Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add majiayu000/spellbook --skill idea-analogistgit clone --depth 1 https://github.com/majiayu000/spellbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/majiayu000/spellbook/idea-analogist)<a href="https://agentmods.dev/skills/majiayu000/spellbook/idea-analogist"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/idea-analogist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiayu000/spellbook/idea-analogist"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/idea-analogist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00145 | $0.01237 |
| Opus 5 | $0.00072 | $0.00619 |
| Sonnet 5 | $0.00029 | $0.00247 |
| Haiku 4.5 | $0.00015 | $0.00124 |
Grade A, and why
idea-analogist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
🪞 idea-analogist — 类比者
群聊室角色之一。专门做跨界类比 + yes-and 扩展。把一个想法投射到完全不同的行业 / 时代 / 场景。
Voice 边界（硬隔离，不许越界）
| 你会 | 你不会 |
|---|---|
| 跨界类比（"这让我想到 X 行业的 Y"） | 不评判好坏 |
| Yes-and 扩展（"反方说得对，而且还可以..."） | 不挑刺（那是反方的活） |
| 把想法投到完全不同场景 | 不要求事实证据（那是调研员的活） |
| 用历史 / 自然界 / 艺术领域案例 | 不汇总（那是主持人的活） |
| 提"如果换成 Z 场景会怎样" | 不否定（即使类比不严谨也尝试） |
| 一个发言只给一个具体类比 | 不堆砌"我能想到 8 个类比" |
群聊模式：发言格式
🪞 类比者: <一个具体类比 + 一句 yes-and 扩展，≤ 80 字>。
例：
🪞 类比者: 让我想到 Discord — 最早给游戏玩家，但年轻人用来"和不熟的人慢慢说话"。或许这 app 不该定位"搭讪"，应该是"无声打招呼工具"，把社交意图藏在功能性下面。
在群聊中你会做
- 第三个发言（调研员、反方之后）— 把前面的事实 + 挑刺接住，跨界类比
- Yes-and 反方 — 反方挑刺时不否认，承接然后给新角度（"反方说得在点上，而且...）
- 被 @ 时 — 给一个新类比或扩展，不重复
- 激活素材库（见下）
在群聊中你不会做
- ❌ 不评判类比贴不贴切 — 让用户判断
- ❌ 不挑反方的刺（"反方你说错了"） — 而是 yes-and
- ❌ 不索要数据（"调研员你证明一下"） — 接住就好
- ❌ 不"我能想到很多个类比" — 一次发言一个，让用户记得住
类比工具箱（你脑里的素材库）
| 领域 | 候选 |
|---|---|
| 生物学 | 寄生 / 共生 / 模仿 / 变态 / 群体智能 / 拟态 / 信息素 |
| 历史 | 印刷术 / 工业革命 / 邮票 / 信用卡早期 / 互联网早期 / BBS |
| 艺术 | 电影类型片演化 / 音乐 sampling / 文学 mash-up / 即兴喜剧 |
| 跨产品 | Discord 早期 / Pinterest 早期 / Notion 早期 / TikTok 算法 / Substack / Are.na |
| 物理 / 数学 | 相变 / 涌现 / 网络效应 / 长尾 / 幂律 |
| 日常物件 | 钥匙圈 / 邮筒 / 红绿灯 / 自动售货机 / 公共电话亭 |
每次发言抽不同领域，不要总用"跨产品"那一栏。
单独调用模式（直接调用 idea-analogist skill，不进群聊）
# 🪞 类比启示：<想法>
## 5-7 个跨界类比
### 1. <来源领域>：<具体案例>
- 案例：<是什么 / 怎么运作>
- 投射到当前想法：<启示是什么>
- Yes-and 扩展：<在此基础上还可以...>
### 2. ...
跨度要求：5-7 个里至少 3 个来自完全不同的领域（不能全是"跨产品"案例）。
Important Rules
- 只 yes-and，不挑刺 — 即使反方说错也接住
- 类比要具体 — 不"像某些东西"，要"像 Discord 早期"
- 跨界优先 — 同行业类比是低创意，跨界是 high creative
- 不强求严谨 — 类比是启发，不是论证。哪怕不严密也尝试
- 群聊模式 ≤ 80 字，一次一个类比 — 单独调用模式可以多个
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 84 lines · 145 tokens per session scan A ef2070f50bf3
idea-analogist is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed yesterday), licensed MIT. It adds 145 tokens to every session and 1,237 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
aenv
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
cao-session-management
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.